Green AI-Based Network Traffic Optimization Using Large Language Models and Digital Twin Wireless Networks
Keywords:
green AI; large language models; digital twin; wireless network traffic optimization; sustainability; network intelligenceAbstract
The escalating energy footprint of next-generation wireless networks demands a fundamental rethinking of traffic optimization architectures. This paper proposes a novel framework that couples large language models with digital twin wireless networks to achieve green AI-driven network management. We examine the system-level integration of semantic reasoning and high-fidelity simulation, investigating the structural trade-offs between model expressiveness, computational overhead, and energy sustainability. The architecture leverages large language models to generate interpretable traffic engineering policies from high-level intents, while a continuously synchronized digital twin serves as a sandbox for stress-testing and zero-energy validation. A central theme is the tension between the substantial carbon cost of training and serving large models and the long-term energy savings realized through proactive, coordinated optimization. We analyze governance mechanisms, fairness preservation, and the robustness of AI-augmented control loops under realistic operational conditions. Furthermore, we explore policy pathways, standardization efforts, and lifecycle carbon accounting needed to embed sustainability into the core of intelligent network infrastructures. The discussion synthesizes insights from distributed intelligence, resource allocation theory, explainable AI, and regulatory design, advocating for an interdisciplinary approach in which performance, equity, and environmental stewardship co-evolve. By framing the integration as a socio-technical system, we highlight how green AI principles can be operationalized at scale, ensuring that next-generation network intelligence does not merely optimize throughput but does so within the planet’s ecological boundaries.
References
1. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 3645–3650). Association for Computational Linguistics.
2. Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020). Green AI. Communications of the ACM, 63(12), 54–63.
3. Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. V. (2021). Digital twin for 6G: A roadmap. IEEE Network, 35(6), 142–149.
4. Liu, Y., Zhang, X., Cui, Y., & Han, Z. (2023). Digital twin in 6G: A comprehensive survey. IEEE Communications Surveys & Tutorials, 25(3), 1579–1621.
5. Wu, S., Li, Z., Xu, Y., & Li, G. Y. (2024). NetLLM: Adapting large language models for networking. In Proceedings of the ACM SIGCOMM 2024 Conference (pp. 1–15). ACM.
6. Xu, J., Sheng, M., Li, J., Liu, J., & Quek, T. Q. S. (2024). Large language models for wireless communications: A comprehensive survey. IEEE Communications Surveys & Tutorials, 26(2), 876–907.
7. Grieves, M., & Vickers, J. (2017). Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems. In F.-J. Kahlen, J. Flumerfelt, & A. Alves (Eds.), Transdisciplinary perspectives on complex systems (pp. 85–113). Springer.
8. Wang, Z., Li, W., & Poslad, S. (2021). A survey on deep learning for network traffic prediction. IEEE Communications Surveys & Tutorials, 23(4), 2684–2727.
9. Buzzi, S., Chih, I., Klein, T. E., Poor, H. V., Tang, W., & Zorzi, M. (2021). A survey of energy-efficient techniques for 5G networks and beyond. IEEE Communications Surveys & Tutorials, 23(2), 765–798.
10. Zhang, S., Xu, X., Wu, Y., Lu, J., & Liu, Y. (2022). Sustainability in 6G: A vision for green communication. IEEE Network, 36(5), 28–34.
11. Yu, B., Yin, H., & Zhu, Z. (2018). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (pp. 3634–3640). AAAI Press.
12. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., ... & Lample, G. (2023). LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
13. Chen, M., Challita, U., Saad, W., Yin, C., & Debbah, M. (2023). Graph neural networks for wireless communications: A survey. IEEE Communications Surveys & Tutorials, 25(1), 1–37.
14. Zhang, C., Zhang, H., Qiao, J., Li, Z., & Alouini, M. S. (2025). TIDES: Traffic Intelligence with DeepSeek Enhanced Spatial Temporal Prediction. IEEE Journal on Selected Areas in Communications.
15. He, Y., Ren, J., Yu, G., & Cai, Y. (2023). Digital twin for wireless networks: A comprehensive architectural framework. IEEE Communications Magazine, 61(4), 54–60.
16. Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., ... & Miao, C. (2020). Federated learning in mobile edge computing: A survey. IEEE Communications Surveys & Tutorials, 22(3), 2031–2063.
17. Sun, W., Liu, J., Zhang, H., & Leung, V. C. M. (2022). Energy-aware task offloading for digital twin-empowered mobile edge computing. IEEE Transactions on Mobile Computing, 21(10), 3592–3606.
18. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2020). Explainable artificial intelligence: A comprehensive review. Information Fusion, 58, 82–115.
19. Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2022). Adversarial machine learning: A systematic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 8858–8881.
20. van Wynsberghe, A. (2021). Sustainable AI: AI for sustainability and the sustainability of AI. AI & Society, 36, 213–218.
21. Vinuesa, R., Azizpour, H., Leite, I., Balaam, M., Dignum, V., Domisch, S., ... & Felländer, A. (2020). The role of artificial intelligence in achieving the Sustainable Development Goals. Nature Communications, 11, Article 233.
22. Li, J., Zhang, G., Li, Y., & Niyato, D. (2023). Digital twin for green networking: A survey. IEEE Communications Surveys & Tutorials, 25(4), 2567–2611.
23. Ma, Y., Zhang, R., Xiao, J., & Chowdhury, K. R. (2024). Conversational AI for network management: A survey. IEEE Network, 38(1), 146–153.
24. Le, L. B., Kaddoum, G., & Cottatellucci, L. (2021). Fairness in wireless resource allocation: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23(3), 1761–1792.
25. Marsch, P., Bulakci, Ö., & Queseth, O. (2020). Regulatory aspects of energy efficiency in 5G networks. IEEE Communications Standards Magazine, 4(3), 22–28.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
